From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping
This addresses the modality gap issue in vision-language models for generation tasks, enabling zero-shot captioning without fine-tuning, though it is incremental as it builds on existing CLIP capabilities.
The paper tackles the problem of applying CLIP to generation tasks like image and video captioning by proposing Knight, a zero-shot method that maps images/videos to language modality, achieving state-of-the-art performance in zero-shot captioning.
With the development of Vision-Language Pre-training Models (VLPMs) represented by CLIP and ALIGN, significant breakthroughs have been achieved for association-based visual tasks such as image classification and image-text retrieval by the zero-shot capability of CLIP without fine-tuning. However, CLIP is hard to apply to generation-based tasks. This is due to the lack of decoder architecture and pre-training tasks for generation. Although previous works have created generation capacity for CLIP through additional language models, a modality gap between the CLIP representations of different modalities and the inability of CLIP to model the offset of this gap, which fails the concept to transfer across modalities. To solve the problem, we try to map images/videos to the language modality and generate captions from the language modality. In this paper, we propose the K-nearest-neighbor Cross-modality Mapping (Knight), a zero-shot method from association to generation. With text-only unsupervised training, Knight achieves State-of-the-Art performance in zero-shot methods for image captioning and video captioning. Our code is available at https://github.com/junyangwang0410/Knight.